Search Results for author:
Found 11 papers, 9 papers with code
MAGMA: Manifold Regularization for MAEs
Masked Autoencoders (MAEs) are an important divide in self-supervised learning (SSL) due to their independence from augmentation techniques for generating positive (and/or negative) pairs as in contrastive frameworks.
MAPL: Model Agnostic Peer-to-peer Learning
Effective collaboration among heterogeneous clients in a decentralized setting is a rather unexplored avenue in the literature.
BECLR: Batch Enhanced Contrastive Few-Shot Learning
Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning.
GeNIe: Generative Hard Negative Images Through Diffusion
To achieve this, we adjust the noise level (equivalently, number of diffusion iterations) to ensure the generated image retains low-level and background features from the source image while representing the target category, resulting in a hard negative sample for the source category.
LAB: Learnable Activation Binarizer for Binary Neural Networks
Binary Neural Networks (BNNs) are receiving an upsurge of attention for bringing power-hungry deep learning towards edge devices.
Self-Attention Message Passing for Contrastive Few-Shot Learning
Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision.
Contrastive Learning
Unsupervised Few-Shot Image Classification
+1
Transductive Decoupled Variational Inference for Few-Shot Classification
The versatility to learn from a handful of samples is the hallmark of human intelligence.
Self-Supervised Class-Cognizant Few-Shot Classification
Unsupervised learning is argued to be the dark matter of human intelligence.
Federated Learning with Taskonomy for Non-IID Data
Classical federated learning approaches incur significant performance degradation in the presence of non-IID client data.
Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation
Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance.
Lookahead Adversarial Learning for Near Real-Time Semantic Segmentation
Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications.
